superlab 0.1.55 → 0.1.57

package/README.md

@@ -331,7 +331,12 @@ If `workflow_language` and `paper_language` differ, `/lab:write` should preserve
 The workflow-language paper layer is a real LaTeX mirror of the paper, not a review layer, and should stay persisted until it is explicitly refreshed.
 Paper-facing tables must be locally interpretable: readers should be able to recover row meaning, column meaning, metric direction, and any relevant denominator or unit from the table title, note, and adjacent prose without chasing the Method section. Short headers are allowed, but abbreviations must be expanded locally in the same table.
 Do not assume a fixed drafting order such as Method before Experiments. If a section needs to use canonical model, system, or ablation labels before the defining section has been drafted, add a short local naming bridge there and then reuse the canonical label instead of drifting into narrative aliases.
+`/lab:write` now also applies a section-specific style policy for Abstract, Introduction, Related Work, Method, Experiments, and Conclusion. Each active section must follow its encouraged moves, avoid discouraged moves, and remove banned expressions before the round can be accepted.
+On the same section, prose tightening is no longer the default next step. Before any extra tighten, compress, or polish pass, the section must pass a pre-polish acceptance gate covering canonical naming consistency, adjacent-section consistency, claim/metric/ranking consistency with evidence, section-style compliance, local clarity, and local concision.
+If a round replaces the paper's canonical experiment or evaluation protocol, `/lab:write` should treat it as a paper-wide protocol replacement unless the user explicitly scopes it as supplementary or appendix-only. That triggers a paper-wide impact audit over affected sections, tables, figures, analysis assets, and `.lab/writing/plan.md` before further polish.
+`/lab:write` should not invent translation-layer or workflow-layer sync work as the next step. Those actions are only valid when the user explicitly asks for them or when the language-finalization workflow requires them.
 If Method or Experiments prose promises a metric family, the main table set must either expose that family directly or explicitly mark missing metrics as appendix-only and explain why.
+Main-table width control should prefer redesign over shrinking: shorten headers while preserving local explanation, move secondary metrics to appendix-only, reduce or split columns, then adjust `\tabcolsep` conservatively. Treat `\resizebox{\linewidth}{!}{...}` as a last resort rather than the default fit strategy.
 At the final export or final-draft boundary, if the project is still on the default scaffold and no attached template exists, ask one final reminder question before finalizing.
 For final-draft or export rounds, `/lab:write` should materialize real LaTeX tables, figure placeholders with figure intent, a non-empty `references.bib`, and pass `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before stopping.
 

package/lib/i18n.cjs

@@ -2052,6 +2052,20 @@ ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "write.md")] = `# \`/l
 - 不要假定固定的写作顺序，例如 Method 一定先于 Experiments；formal naming 可以先在 Method、Experiments 或其他 section 里出现。
 - 如果某个 section 必须先用 canonical short names、model labels 或 ablation labels，而正式定义这些命名的 section 还没写到，就在当前 section 先做一次本地命名桥接（local naming bridge），用一句简短映射把解释性短语对齐到 canonical 的 paper-facing labels，然后后文统一复用这些 canonical labels。
 - 一旦 paper-facing 模型名或消融名锁定，后续 prose、表格、caption 和排序摘要都必须复用 canonical label，不要再换回“完整模型”“去除结构主干”这类叙述性别名。
+- 起草或润色前，先检查当前 section 在 \`section-style-policies.md\` 里的规则块，并遵守其中的 encouraged expressions、discouraged expressions 和 banned expressions / moves。
+- 不要默认当前 section 可以无限继续压句子；在同一个 section 上做新的 tighten、compress 或 polish 之前，先过一遍 section-level acceptance gate。
+- section-level acceptance gate 至少要显式确认命名一致性、前后文一致性、claim / metric / ranking 与当前证据的一致性、局部清晰度、局部简洁度和 section 风格合规（section-style compliance）。
+- 如果当前 section 还包含 \`section-style-policies.md\` 里列出的禁用表达、禁用修辞动作或 banned expressions / moves，就说明这一轮还没有通过 section-level acceptance gate。
+- 如果本轮改动的是论文当前的 canonical 实验或评测协议（例如 split 比例、训练/测试规模、seed 或 split 数量、benchmark 集合、主表评测口径），默认把它当成主协议替换，而不是补充实验；除非用户明确说这是 supplementary 或 appendix-only。
+- 遇到这种主协议替换时，先做全文影响审计（paper-wide impact audit），列出哪些 section 和资产已经过期，优先更新影响最大的 canonical section / asset，再继续润色。
+- 不要默认去做 translation/workflow-layer 同步；只有用户明确要求，或者语言最终定稿流程要求这样做时，才进入这类动作。
+- 如果任何一项还没过，就先解决这个 blocker，而不是继续做 prose polish。
+- 不要把下一步建议默认写成“继续收紧一轮”；应该优先指出第一个没过的 acceptance item，或者在本轮已接受时直接停止。
+- 不要把 \`\\resizebox{\\linewidth}{!}{...}\` 当成主表默认的宽度解决方案。
+- 主表如果超宽，先重构表：缩短表头但保留局部解释，把次要指标移到 appendix-only，减少或拆分列，最后才保守调整 \`\\tabcolsep\`；只有这些都做过仍然超宽时，才允许把 \`\\resizebox\` 当成最后手段。
+- 调整 \`\\tabcolsep\` 时保持保守，不要把 paper-facing 主表压到大约 \`3pt\` 以下；优先用 \`4pt\` 或 \`5pt\` 这类仍可读的范围。
+- 不要把 \`\\scriptsize\` 或 \`\\tiny\` 当成主表默认的适配策略；如果必须靠激进缩小字体才能塞进页面，优先重构表本身。
+- 如果主表使用了 \`\\resizebox\` 或非常规宽度控制，就在同一张表的表注里解释宽度处理理由。
 - reader-facing prose 里不要使用包含 \`_\` 或 \`-\` 的标签名。
 - 内部标识符、配置键和实验包标签默认不要进正文；若必须出现，也只能给读者映射一次，然后移回正文之外。
 - 不要靠堆术语来制造学术感；如果本轮引入或改写了关键术语，就在用户可见的轮次总结里补一段简短术语说明，并把 terminology-clarity 自检写进 write iteration artifact。
@@ -2065,6 +2079,9 @@ ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "write.md")] = `# \`/l
 - 如果 \`paper-plan\` 校验失败，就先补 \`.lab/writing/plan.md\`，不能直接跳去写 prose。
 - 普通草稿轮次在改完当前 section 后，必须运行 \`.lab/.managed/scripts/validate_section_draft.py --section <section> --section-file <section-file> --mode draft\` 和 \`.lab/.managed/scripts/validate_paper_claims.py --section-file <section-file> --mode draft\`。
 - 普通草稿轮次里，这两类校验先按 warning 处理；warning 必须写进 write iteration artifact，不能假装没看到。
+- 如果要建议继续 tighten、compress 或 polish 同一个 section，必须先把 section-level acceptance gate 写进 write iteration artifact。
+- 在 write iteration artifact 里记录当前 section 的 section-style policy 合规性、保留了哪些 discouraged move 及其理由、以及是否还存在任何禁用表达。
+- 如果本轮替换或重写了 canonical 实验/评测协议，就把 protocol/scope impact audit 也写进 write iteration artifact。
 - \`paper-plan\` 里还必须写清资产覆盖目标、问题设定或 teaser 图，以及一个额外 analysis asset。
 - 最终定稿或导出轮次里，必须维护非空的 \`references.bib\`，并把关键实验结果物化成真正的 LaTeX 表格：
   - \`<deliverables_root>/paper/tables/main-results.tex\`

package/lib/lab_write_contract.json

@@ -1,8 +1,8 @@
 {
   "stage_prompt": {
-    "codex_en": "This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.",
-    "claude_en": "This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.",
-    "codex_zh": "本命令运行 `/lab:write` 阶段。把 `.codex/skills/lab/stages/write.md` 当成模板选择、paper-plan、section 参考、校验 gate、资产覆盖和最终 manuscript 规则的单一来源。读取与当前 section 对应的 paper-writing reference 和 bundled example-bank 文件，一次只修改一个 section；普通草稿轮次把写作校验当 warning，最终定稿或导出轮次必须满足 write-stage 的接受 gate。普通起草轮次先跟随 `workflow_language`，普通 `.tex` section 草稿也必须先停留在 `workflow_language`，不能把 `paper_language` 当成默认草稿语言，并把 workflow-language 论文层当成正式持久化产物，而不是 review 层。workflow-language 层必须是一套完整的 LaTeX 镜像，至少包含 `workflow-language/main.tex`、`workflow-language/references.bib`、`workflow-language/sections/*.tex`、`workflow-language/tables/*.tex`、`workflow-language/figures/*.tex` 和 `workflow-language/analysis/analysis-asset.tex`。不要再把新的 workflow-language 输出写到已经废弃的 review 层路径，例如 `docs/lab/paper/review_zh/`。把 `.lab/writing/terminology-glossary.md` 作为写作期 glossary，用来沉淀全称、批准缩写、对外解释和可接受别名。无论当前语言是什么，都要满足同一套学术可读性标准：如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就先写全称；如果后面要复用短写，就在首次出现时定义；同时说明它是什么、为什么在这里重要，保持一个概念只有一个 paper-facing 名称，并尽量避免新造的连字符拼接标签。相同的首次解释规则也适用于表头、caption、表注和图注；如果术语第一次出现在表里，就必须在同一张表里局部解释。主表必须局部自足：读者只看表题、表头、表注和邻近引入或解读，就应当知道每行是什么、每列是什么、指标方向是什么，以及需要的单位、分母或触发条件。表头可以短，但表里的缩写必须在同表局部展开。如果 Method 或 Experiments 承诺了一组指标，主表就必须直接展示这些指标，或者明确标成 appendix-only 并解释原因；如果某个指标因为恒为零、冗余或只放附录而不单列，也必须在表注里显式说明，不能静默省略。内部标识符默认不要进入 reader-facing prose；若必须出现，只能在完成一次读者映射后使用，并把 terminology-clarity 自检和 table-semantics 审计一起写进 write iteration artifact。如果当前稿件将从托管默认 scaffold 开始，且还没有模板决定，就先追问一次：继续使用默认 scaffold，还是先接入模板目录。如果进入最终定稿时 `workflow_language` 与 `paper_language` 不一致，就先完成并保留 workflow-language 论文层，再追问一次：保持当前语言，还是把 canonical manuscript 转成 `paper_language`；先持久化这个决定，再在最新 write iteration 里记录语言决策和 workflow-language 论文层路径，最后才允许按该语言修改最终稿。",
-    "claude_zh": "本命令运行 lab workflow 的 `write` 阶段。把 `.claude/skills/lab/stages/write.md` 当成模板选择、paper-plan、section 参考、校验 gate、资产覆盖和最终 manuscript 规则的单一来源。读取与当前 section 对应的 paper-writing reference 和 bundled example-bank 文件，一次只修改一个 section；普通草稿轮次把写作校验当 warning，最终定稿或导出轮次必须满足 write-stage 的接受 gate。普通起草轮次先跟随 `workflow_language`，普通 `.tex` section 草稿也必须先停留在 `workflow_language`，不能把 `paper_language` 当成默认草稿语言，并把 workflow-language 论文层当成正式持久化产物，而不是 review 层。workflow-language 层必须是一套完整的 LaTeX 镜像，至少包含 `workflow-language/main.tex`、`workflow-language/references.bib`、`workflow-language/sections/*.tex`、`workflow-language/tables/*.tex`、`workflow-language/figures/*.tex` 和 `workflow-language/analysis/analysis-asset.tex`。不要再把新的 workflow-language 输出写到已经废弃的 review 层路径，例如 `docs/lab/paper/review_zh/`。把 `.lab/writing/terminology-glossary.md` 作为写作期 glossary，用来沉淀全称、批准缩写、对外解释和可接受别名。无论当前语言是什么，都要满足同一套学术可读性标准：如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就先写全称；如果后面要复用短写，就在首次出现时定义；同时说明它是什么、为什么在这里重要，保持一个概念只有一个 paper-facing 名称，并尽量避免新造的连字符拼接标签。相同的首次解释规则也适用于表头、caption、表注和图注；如果术语第一次出现在表里，就必须在同一张表里局部解释。主表必须局部自足：读者只看表题、表头、表注和邻近引入或解读，就应当知道每行是什么、每列是什么、指标方向是什么，以及需要的单位、分母或触发条件。表头可以短，但表里的缩写必须在同表局部展开。如果 Method 或 Experiments 承诺了一组指标，主表就必须直接展示这些指标，或者明确标成 appendix-only 并解释原因；如果某个指标因为恒为零、冗余或只放附录而不单列，也必须在表注里显式说明，不能静默省略。内部标识符默认不要进入 reader-facing prose；若必须出现，只能在完成一次读者映射后使用，并把 terminology-clarity 自检和 table-semantics 审计一起写进 write iteration artifact。如果当前稿件将从托管默认 scaffold 开始，且还没有模板决定，就先追问一次：继续使用默认 scaffold，还是先接入模板目录。如果进入最终定稿时 `workflow_language` 与 `paper_language` 不一致，就先完成并保留 workflow-language 论文层，再追问一次：保持当前语言，还是把 canonical manuscript 转成 `paper_language`；先持久化这个决定，再在最新 write iteration 里记录语言决策和 workflow-language 论文层路径，最后才允许按该语言修改最终稿。"
+    "codex_en": "This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\\resizebox{\\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\\tabcolsep` conservatively; only use `\\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\\scriptsize` or `\\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.",
+    "claude_en": "This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\\resizebox{\\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\\tabcolsep` conservatively; only use `\\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\\scriptsize` or `\\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.",
+    "codex_zh": "本命令运行 `/lab:write` 阶段。把 `.codex/skills/lab/stages/write.md` 当成模板选择、paper-plan、section 参考、校验 gate、资产覆盖和最终 manuscript 规则的单一来源。读取与当前 section 对应的 paper-writing reference、`section-style-policies.md` 里与当前 section 对应的风格块，以及 bundled example-bank 文件，一次只修改一个 section；普通草稿轮次把写作校验当 warning，最终定稿或导出轮次必须满足 write-stage 的接受 gate。普通起草轮次先跟随 `workflow_language`，普通 `.tex` section 草稿也必须先停留在 `workflow_language`，不能把 `paper_language` 当成默认草稿语言，并把 workflow-language 论文层当成正式持久化产物，而不是 review 层。workflow-language 层必须是一套完整的 LaTeX 镜像，至少包含 `workflow-language/main.tex`、`workflow-language/references.bib`、`workflow-language/sections/*.tex`、`workflow-language/tables/*.tex`、`workflow-language/figures/*.tex` 和 `workflow-language/analysis/analysis-asset.tex`。不要再把新的 workflow-language 输出写到已经废弃的 review 层路径，例如 `docs/lab/paper/review_zh/`。把 `.lab/writing/terminology-glossary.md` 作为写作期 glossary，用来沉淀全称、批准缩写、对外解释和可接受别名。无论当前语言是什么，都要满足同一套学术可读性标准：如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就先写全称；如果后面要复用短写，就在首次出现时定义；同时说明它是什么、为什么在这里重要，保持一个概念只有一个 paper-facing 名称，并尽量避免新造的连字符拼接标签。相同的首次解释规则也适用于表头、caption、表注和图注；如果术语第一次出现在表里，就必须在同一张表里局部解释。不要假定当前 section 可以无限继续压句子；在同一个 section 上做新的 tighten、compress 或 polish 之前，先过一遍 section-level acceptance gate。这个 gate 至少要显式确认命名一致性、前后文一致性、claim / metric / ranking 与当前证据的一致性、局部清晰度、局部简洁度，以及 section-style compliance。当前 section 的写作表达必须先遵守 `section-style-policies.md` 里的鼓励表达、谨慎表达和禁用表达；只要还有禁用表达或禁用写法残留，本轮就不能算通过 section-level acceptance gate。如果本轮改动的是论文当前的 canonical 实验或评测协议（例如 split 比例、训练/测试规模、seed 或 split 数量、benchmark 集合、主表评测口径），默认把它当成主协议替换，而不是补充实验；除非用户明确说这是 supplementary 或 appendix-only。遇到这种协议替换时，先做全文影响审计（paper-wide impact audit），列出哪些 section 和资产已经过期，优先更新影响最大的 canonical section / asset，再继续润色；不要默认去做 translation/workflow-layer 同步，除非用户明确要求，或者语言最终定稿流程要求这样做。如果任何一项还没过，就先解决这个 blocker，不要默认继续 prose polish，也不要把下一步建议自动写成“再收紧一轮”。主表必须局部自足：读者只看表题、表头、表注和邻近引入或解读，就应当知道每行是什么、每列是什么、指标方向是什么，以及需要的单位、分母或触发条件。表头可以短，但表里的缩写必须在同表局部展开。如果 Method 或 Experiments 承诺了一组指标，主表就必须直接展示这些指标，或者明确标成 appendix-only 并解释原因；如果某个指标因为恒为零、冗余或只放附录而不单列，也必须在表注里显式说明，不能静默省略。不要把 `\\resizebox{\\linewidth}{!}{...}` 当成主表默认的宽度解决方案。主表如果超宽，先重构表：缩短表头但保留局部解释，把次要指标移到 appendix-only，减少或拆分列，最后才保守调整 `\\tabcolsep`；只有这些都做过仍然超宽时，才允许把 `\\resizebox` 当成最后手段，而且必须在同一张表的表注里解释宽度处理理由。不要把 `\\scriptsize` 或 `\\tiny` 当成主表默认的适配策略。内部标识符默认不要进入 reader-facing prose；若必须出现，只能在完成一次读者映射后使用，并把 terminology-clarity 自检、section-level acceptance gate、section-style policy 合规检查、protocol/scope impact audit 和 table-semantics 审计一起写进 write iteration artifact。如果当前稿件将从托管默认 scaffold 开始，且还没有模板决定，就先追问一次：继续使用默认 scaffold，还是先接入模板目录。如果进入最终定稿时 `workflow_language` 与 `paper_language` 不一致，就先完成并保留 workflow-language 论文层，再追问一次：保持当前语言，还是把 canonical manuscript 转成 `paper_language`；先持久化这个决定，再在最新 write iteration 里记录语言决策和 workflow-language 论文层路径，最后才允许按该语言修改最终稿。",
+    "claude_zh": "本命令运行 lab workflow 的 `write` 阶段。把 `.claude/skills/lab/stages/write.md` 当成模板选择、paper-plan、section 参考、校验 gate、资产覆盖和最终 manuscript 规则的单一来源。读取与当前 section 对应的 paper-writing reference、`section-style-policies.md` 里与当前 section 对应的风格块，以及 bundled example-bank 文件，一次只修改一个 section；普通草稿轮次把写作校验当 warning，最终定稿或导出轮次必须满足 write-stage 的接受 gate。普通起草轮次先跟随 `workflow_language`，普通 `.tex` section 草稿也必须先停留在 `workflow_language`，不能把 `paper_language` 当成默认草稿语言，并把 workflow-language 论文层当成正式持久化产物，而不是 review 层。workflow-language 层必须是一套完整的 LaTeX 镜像，至少包含 `workflow-language/main.tex`、`workflow-language/references.bib`、`workflow-language/sections/*.tex`、`workflow-language/tables/*.tex`、`workflow-language/figures/*.tex` 和 `workflow-language/analysis/analysis-asset.tex`。不要再把新的 workflow-language 输出写到已经废弃的 review 层路径，例如 `docs/lab/paper/review_zh/`。把 `.lab/writing/terminology-glossary.md` 作为写作期 glossary，用来沉淀全称、批准缩写、对外解释和可接受别名。无论当前语言是什么，都要满足同一套学术可读性标准：如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就先写全称；如果后面要复用短写，就在首次出现时定义；同时说明它是什么、为什么在这里重要，保持一个概念只有一个 paper-facing 名称，并尽量避免新造的连字符拼接标签。相同的首次解释规则也适用于表头、caption、表注和图注；如果术语第一次出现在表里，就必须在同一张表里局部解释。不要假定当前 section 可以无限继续压句子；在同一个 section 上做新的 tighten、compress 或 polish 之前，先过一遍 section-level acceptance gate。这个 gate 至少要显式确认命名一致性、前后文一致性、claim / metric / ranking 与当前证据的一致性、局部清晰度、局部简洁度，以及 section-style compliance。当前 section 的写作表达必须先遵守 `section-style-policies.md` 里的鼓励表达、谨慎表达和禁用表达；只要还有禁用表达或禁用写法残留，本轮就不能算通过 section-level acceptance gate。如果本轮改动的是论文当前的 canonical 实验或评测协议（例如 split 比例、训练/测试规模、seed 或 split 数量、benchmark 集合、主表评测口径），默认把它当成主协议替换，而不是补充实验；除非用户明确说这是 supplementary 或 appendix-only。遇到这种协议替换时，先做全文影响审计（paper-wide impact audit），列出哪些 section 和资产已经过期，优先更新影响最大的 canonical section / asset，再继续润色；不要默认去做 translation/workflow-layer 同步，除非用户明确要求，或者语言最终定稿流程要求这样做。如果任何一项还没过，就先解决这个 blocker，不要默认继续 prose polish，也不要把下一步建议自动写成“再收紧一轮”。主表必须局部自足：读者只看表题、表头、表注和邻近引入或解读，就应当知道每行是什么、每列是什么、指标方向是什么，以及需要的单位、分母或触发条件。表头可以短，但表里的缩写必须在同表局部展开。如果 Method 或 Experiments 承诺了一组指标，主表就必须直接展示这些指标，或者明确标成 appendix-only 并解释原因；如果某个指标因为恒为零、冗余或只放附录而不单列，也必须在表注里显式说明，不能静默省略。不要把 `\\resizebox{\\linewidth}{!}{...}` 当成主表默认的宽度解决方案。主表如果超宽，先重构表：缩短表头但保留局部解释，把次要指标移到 appendix-only，减少或拆分列，最后才保守调整 `\\tabcolsep`；只有这些都做过仍然超宽时，才允许把 `\\resizebox` 当成最后手段，而且必须在同一张表的表注里解释宽度处理理由。不要把 `\\scriptsize` 或 `\\tiny` 当成主表默认的适配策略。内部标识符默认不要进入 reader-facing prose；若必须出现，只能在完成一次读者映射后使用，并把 terminology-clarity 自检、section-level acceptance gate、section-style policy 合规检查、protocol/scope impact audit 和 table-semantics 审计一起写进 write iteration artifact。如果当前稿件将从托管默认 scaffold 开始，且还没有模板决定，就先追问一次：继续使用默认 scaffold，还是先接入模板目录。如果进入最终定稿时 `workflow_language` 与 `paper_language` 不一致，就先完成并保留 workflow-language 论文层，再追问一次：保持当前语言，还是把 canonical manuscript 转成 `paper_language`；先持久化这个决定，再在最新 write iteration 里记录语言决策和 workflow-language 论文层路径，最后才允许按该语言修改最终稿。"
   }
 }

package/package-assets/claude/commands/lab/write.md

@@ -7,4 +7,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.claude/skills/lab/SKILL.md`.
 
 Execute the requested `/lab-write` command against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/claude/commands/lab-write.md

@@ -7,4 +7,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.claude/skills/lab/SKILL.md`.
 
 Execute the requested `/lab-write` command against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/claude/commands/lab:write.md

@@ -7,4 +7,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.claude/skills/lab/SKILL.md`.
 
 Execute the requested `/lab-write` command against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/claude/commands/lab/357/274/232write.md

@@ -7,4 +7,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.claude/skills/lab/SKILL.md`.
 
 Execute the requested `/lab-write` command against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/codex/prompts/lab/write.md

@@ -6,4 +6,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.codex/skills/lab/SKILL.md`.
 
 Execute the requested `/lab:write` stage against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/codex/prompts/lab-write.md

@@ -6,4 +6,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.codex/skills/lab/SKILL.md`.
 
 Execute the requested `/lab:write` stage against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/codex/prompts/lab:write.md

@@ -6,4 +6,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.codex/skills/lab/SKILL.md`.
 
 Execute the requested `/lab:write` stage against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/codex/prompts/lab/357/274/232write.md

@@ -6,4 +6,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.codex/skills/lab/SKILL.md`.
 
 Execute the requested `/lab:write` stage against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record both the terminology-clarity self-check and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference, the current section block in `section-style-policies.md`, and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat the workflow-language paper layer as a real persisted artifact rather than a review layer, and preserve it as a full LaTeX mirror with `workflow-language/main.tex`, `workflow-language/references.bib`, `workflow-language/sections/*.tex`, `workflow-language/tables/*.tex`, `workflow-language/figures/*.tex`, and `workflow-language/analysis/analysis-asset.tex`. Do not write new workflow-language output to deprecated review-layer paths such as `docs/lab/paper/review_zh/`. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, do not use labels containing `_` or `-` in reader-facing prose, apply the same first-mention rule to table headers, table captions, table notes, and figure captions or labels, do not assume a fixed drafting order such as Method before Experiments, add a local naming bridge when a section uses canonical short names before their defining section has been drafted, and reuse the canonical label instead of replacing it with a narrative alias. Follow the current section's encouraged, discouraged, and banned expression lists from `section-style-policies.md`; section-specific banned expressions take priority over prose-polish goals. Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first. That gate must explicitly confirm naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance. If the round changes the paper's canonical experiment or evaluation protocol, treat that change as a canonical replacement unless the user explicitly scoped it as supplementary or appendix-only, run a paper-wide impact audit before more polishing, update the highest-impact stale sections and assets first, and do not default to translation/workflow-layer sync work unless the user explicitly asked for it or the language-finalization workflow requires it. If any gate item is unresolved, or if a banned expression or move from the current section policy remains, spend the round fixing that blocker instead of polishing sentences further, and do not default the next-step recommendation to another polish pass. Main tables must be locally self-contained: the title, header, note, and adjacent prose should tell the reader what each row and column means, the metric direction, and any relevant unit, denominator, or event condition. Short headers remain allowed, but abbreviations in paper-facing tables must be expanded locally in the same table. If Method or Experiments prose promises a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why. If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that disposition explicitly in the table note instead of silently dropping it. Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table. Fit main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort, keep width changes readable, and explain the width-control rationale locally in the same table note. Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check, the section-level acceptance gate, section-style policy compliance, the protocol/scope impact audit, and the table-semantics audit in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language paper layer first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language paper-layer path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/shared/lab/.managed/scripts/validate_manuscript_delivery.py

@@ -29,6 +29,7 @@ REQUIRED_TABLE_NOTE_MARKERS = (
     "% Comparison scope:",
     "% Important caveat:",
 )
+WIDTH_CONTROL_NOTE_MARKER = "% Width control:"
 TABLE_ABBREVIATION_EXCEPTIONS = {"TODO", "TBD"}
 
 
@@ -187,6 +188,20 @@ def check_table_file(path: Path, issues: list[str], label: str):
     for token in sorted(detect_uppercase_abbreviations(text)):
         if not has_local_abbreviation_expansion(local_context, token):
             issues.append(f"{label} uses abbreviation `{token}` without local expansion")
+    has_width_control_note = WIDTH_CONTROL_NOTE_MARKER in text
+    if r"\resizebox{" in text and not has_width_control_note:
+        issues.append(f"{label} uses \\resizebox without a local width-control note")
+    if r"\setlength{\tabcolsep}" in text and not has_width_control_note:
+        issues.append(f"{label} adjusts \\tabcolsep without a local width-control note")
+    if r"\scriptsize" in text or r"\tiny" in text:
+        issues.append(f"{label} must not use \\scriptsize or \\tiny as the default main-table fit strategy")
+    for match in re.finditer(r"\\setlength\{\\tabcolsep\}\{([0-9]+(?:\.[0-9]+)?)pt\}", text):
+        try:
+            value = float(match.group(1))
+        except ValueError:
+            continue
+        if value < 3.0:
+            issues.append(f"{label} sets \\tabcolsep below the safe range for paper-facing main tables")
 
 
 def check_figure_file(path: Path, issues: list[str], label: str):

package/package-assets/shared/lab/.managed/scripts/validate_section_draft.py

@@ -34,6 +34,211 @@ def contains_any(text: str, needles: tuple[str, ...]) -> bool:
     return any(needle.lower() in lowered for needle in needles)
 
 
+def strip_latex_commands(text: str) -> str:
+    text = re.sub(r"%.*", " ", text)
+    text = re.sub(r"\\[A-Za-z@*]+(?:\[[^\]]*\])?", " ", text)
+    text = text.replace("{", " ").replace("}", " ")
+    return text
+
+
+def has_local_naming_bridge(text: str) -> bool:
+    return contains_any(
+        text,
+        (
+            "we denote",
+            "we refer to",
+            "we call",
+            "hereafter",
+            "简称为",
+            "记为",
+            "记作",
+            "下文记为",
+            "以下记为",
+        ),
+    )
+
+
+SECTION_STYLE_WARNINGS = {
+    "abstract": [
+        (
+            "roadmap-style abstract narration",
+            (
+                "in this paper, we first",
+                "we first introduce",
+                "then we",
+                "finally we",
+                "本文首先",
+                "然后我们",
+                "最后我们",
+            ),
+        ),
+    ],
+    "introduction": [
+        (
+            "empty macro-importance hype",
+            (
+                "increasingly critical",
+                "more important than ever",
+                "rapidly becoming essential",
+                "日益重要",
+                "越来越关键",
+                "比以往任何时候都更重要",
+            ),
+        ),
+    ],
+    "related-work": [
+        (
+            "laundry-list related-work framing",
+            (
+                "paper a does",
+                "paper b does",
+                "paper c does",
+                "x does",
+                "y does",
+                "z does",
+            ),
+        ),
+    ],
+    "method": [
+        (
+            "marketing-style or self-promotional wording",
+            (
+                "elegant and powerful",
+                "powerful and elegant",
+                "dramatically stronger",
+                "remarkably strong",
+                "优雅而强大",
+                "强大而优雅",
+                "显著更强",
+                "极其强大",
+            ),
+        ),
+    ],
+    "experiments": [
+        (
+            "meta-reader guidance",
+            (
+                "this way the reader can",
+                "the reader can first",
+                "the reader can then",
+                "helps the reader",
+                "这样读者可以",
+                "读者可以先",
+                "读者可以再",
+            ),
+        ),
+        (
+            "self-evaluative result phrasing",
+            (
+                "results are very clear",
+                "the results are clear",
+                "the defense results are clear",
+                "结果也很清楚",
+                "结果很清楚",
+                "防御结果也很清楚",
+            ),
+        ),
+        (
+            "layout-process commentary",
+            (
+                "page-width adaptive layout",
+                "adaptive layout here",
+                "because the table has many columns",
+                "页宽自适应排版",
+                "因为表列较多",
+                "这里采用页宽",
+            ),
+        ),
+    ],
+    "conclusion": [
+        (
+            "hype-style field transformation claim",
+            (
+                "opens a new era",
+                "transform the field",
+                "redefines the field",
+                "开启一个新时代",
+                "改变整个领域",
+                "重塑整个领域",
+            ),
+        ),
+    ],
+}
+
+
+def check_common_section_gate_risks(text: str, issues: list[str]):
+    prose_text = strip_latex_commands(text)
+    if re.search(r"\b[a-z0-9]+(?:_[a-z0-9]+)+\b", prose_text):
+        issues.append(
+            "reader-facing prose appears to contain internal identifier-like tokens; map them once for the reader and move them back out of prose before more polishing"
+        )
+    if contains_any(
+        prose_text,
+        (
+            "workflow-language",
+            "translation_zh",
+            "review_zh",
+            "deliverables_root",
+            "docs/lab/paper/",
+            "sync this wording",
+            "同步到 translation",
+            "翻到 translation",
+        ),
+    ):
+        issues.append(
+            "paper prose appears to mention workflow-control or translation-layer terms; keep manuscript text on scientific content and move layer-sync notes out of the paper draft"
+        )
+
+    comparison_context = contains_any(
+        prose_text,
+        (
+            "compare",
+            "comparison",
+            "ablation",
+            "variant",
+            "baseline",
+            "ranking",
+            "models",
+            "比较",
+            "消融",
+            "变体",
+            "基线",
+            "排序",
+            "模型",
+        ),
+    )
+    descriptive_alias_risk = contains_any(
+        prose_text,
+        (
+            "full model",
+            "complete model",
+            "variant that removes",
+            "variant without",
+            "removes calibration",
+            "removes the structure",
+            "完整模型",
+            "完整版本",
+            "去除",
+            "移除",
+            "不含",
+            "不带",
+        ),
+    )
+    if comparison_context and descriptive_alias_risk and not has_local_naming_bridge(prose_text):
+        issues.append(
+            "comparative section appears to introduce descriptive variant aliases without an explicit local naming bridge; stabilize canonical labels before more prose polish"
+        )
+
+
+def check_section_style_policy(text: str, section: str, issues: list[str]):
+    prose_text = strip_latex_commands(text)
+    for message, needles in SECTION_STYLE_WARNINGS.get(section, []):
+        if contains_any(prose_text, needles):
+            issues.append(
+                f"{section} section contains {message}; rewrite it to follow the section-style policy before more polishing"
+            )
+
+
 def check_abstract(text: str, issues: list[str]):
     numbers = re.findall(r"\b\d+(?:\.\d+)?\b", text)
     if len(numbers) > 6:
@@ -161,6 +366,8 @@ def main():
 
     text = read_text(section_path)
     issues: list[str] = []
+    check_common_section_gate_risks(text, issues)
+    check_section_style_policy(text, args.section, issues)
     SECTION_CHECKS[args.section](text, issues)
 
     if not issues:

package/package-assets/shared/lab/.managed/templates/paper-table.tex

@@ -15,4 +15,5 @@ Baseline & 0.0000 & 0.0000 \\
 % Metric definitions: expand local abbreviations, units, denominators, or event conditions.
 % Comparison scope: explain which setting, split, attack family, or benchmark scope this table covers.
 % Important caveat: state any omitted metrics, zero-valued metrics, or appendix-only reporting decision.
+% Width control: first shorten headers, move secondary metrics out of the main table, and reduce or split columns; only then adjust \setlength{\tabcolsep}{...} conservatively or use \resizebox{\linewidth}{!}{...} as a documented last resort.
 \end{table}

package/package-assets/shared/lab/.managed/templates/write-iteration.md

@@ -40,6 +40,22 @@
 - Did any alias drift remain unresolved:
 - Remaining reader-facing jargon risk:
 
+## Section Acceptance Gate
+
+- Canonical naming consistency passed:
+- Adjacent-section consistency passed:
+- Claim / metric / ranking consistency with evidence passed:
+- Section-style compliance passed:
+- Local clarity passed:
+- Local concision passed:
+- If any item failed, what blocks further prose polish:
+
+## Section Style Policy
+
+- Section-style policy checked:
+- Any discouraged move kept and why:
+- Any banned move found:
+
 ## Table Semantics
 
 - Metrics promised in Method:
@@ -59,6 +75,14 @@
 - Why this decision was chosen:
 - Workflow-language deliverable path:
 
+## Protocol / Scope Impact Audit
+
+- Did this round replace a canonical experiment or evaluation protocol:
+- If yes, which sections/assets are now stale:
+- Was the paper plan updated before further polish:
+- Was the change explicitly scoped as supplementary/appendix-only by the user:
+- Did any translation/workflow-layer sync get proposed or executed, and why:
+
 ## Decision
 
 - Continue or stop:

package/package-assets/shared/skills/lab/SKILL.md

@@ -224,12 +224,25 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - If a section uses canonical short names or variant labels before the section that formally defines them has been drafted, add a local naming bridge in that section and then keep those labels stable.
 - Keep one canonical natural-language paper-facing name per concept.
 - Once a paper-facing model or ablation label is chosen, reuse the canonical label instead of replacing it with a narrative alias in later prose, tables, or captions.
+- Before drafting or polishing, check the current section block in `skills/lab/references/paper-writing/section-style-policies.md` and follow its encouraged, discouraged, and banned expression lists.
+- Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first.
+- The section-level acceptance gate must explicitly check canonical naming consistency, adjacent-section consistency, claim/metric/ranking consistency with evidence, local clarity, local concision, and section-style compliance.
+- If the current section still contains a banned expression or banned rhetorical move from the section-style policy, the round has not passed the section-level acceptance gate.
+- If a round changes the paper's canonical experiment or evaluation protocol (split ratio, train/test size, seed or split count, benchmark set, or main-table evaluation contract), treat that change as a canonical protocol replacement unless the user explicitly scopes it as supplementary or appendix-only.
+- A canonical protocol replacement requires a paper-wide impact audit before more polishing: identify stale sections and assets across Abstract, Introduction, Method, Experiments, Conclusion, tables, figures, analysis assets, and `.lab/writing/plan.md`, then update the plan and highest-impact stale targets first.
+- When a paper-wide impact audit is still open, default the next write action to the highest-impact canonical stale section or asset instead of another polish pass on the current section.
+- Do not propose or execute translation/workflow-layer synchronization unless the user explicitly asked for it or the language-finalization workflow requires it.
+- If any section-level acceptance item is unresolved, spend the round fixing that blocker instead of polishing sentences further.
 - Use natural-language full names in prose, and define any approved short form once before reusing it.
 - Do not use labels containing `_` or `-` in reader-facing prose.
 - Main tables must be locally self-contained: a reader should be able to understand row meaning, column meaning, metric direction, and any relevant unit or denominator from the table title, table note, and adjacent prose without chasing the Method section.
 - If Method or Experiments prose promises a metric family, the main table set must either expose that metric family directly or mark the missing items as appendix-only and explain why.
 - Short table headers are allowed, but any abbreviation in a paper-facing table must be expanded locally in the same table.
 - If a metric is measured but omitted because it is zero everywhere, redundant, or appendix-only, state that decision explicitly in the table note instead of silently dropping it.
+- Do not treat `\resizebox{\linewidth}{!}{...}` as the default main-table fit strategy.
+- Fit paper-facing main tables by redesign first: shorten headers, move secondary metrics out of the main table, reduce or split columns, then adjust `\tabcolsep` conservatively; only use `\resizebox` as a last resort and document why.
+- Keep `\tabcolsep` adjustments conservative and avoid shrinking below a roughly readable floor for paper-facing main tables.
+- Do not rely on `\scriptsize` or `\tiny` as the default way to make a main table fit.
 - Keep internal identifiers out of prose unless they are mapped once for the reader and then moved back out of prose.
 - Do not rely on unexplained jargon density as a substitute for academic tone.
 - Bind each claim to evidence from `report`, iteration reports, or normalized summaries.
@@ -241,6 +254,9 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - Keep terminology stable across rounds and sections.
 - Maintain `.lab/writing/terminology-glossary.md` as the write-stage source for full forms, approved short forms, reader-facing explanations, allowed aliases, and terms that should stay out of prose.
 - When a round introduces or revises key terms, include a compact terminology note in the user-facing write summary and record the terminology-clarity self-check in the latest write iteration artifact.
+- Record the section-level acceptance gate in the latest write iteration artifact before recommending another tighten/compress/polish pass on the same section.
+- Record section-style policy compliance, any retained discouraged move, and any banned move found in the latest write iteration artifact.
+- Record the protocol/scope impact audit in the latest write iteration artifact whenever a round replaces or rewrites a canonical experiment/evaluation protocol.
 - If a claim is not supported by evidence, weaken or remove it.
 - Treat tables, figures, citations, and bibliography as core manuscript content rather than optional polish.
 - Keep paper-facing LaTeX free of absolute local paths, rerun ids, shell transcripts, and internal workflow provenance.

package/package-assets/shared/skills/lab/references/paper-writing/section-style-policies.md

@@ -0,0 +1,136 @@
+# Section-Style Policies
+
+Use this reference together with the section-specific writing guide. Load only the target section's block for the current round.
+
+Each block defines:
+- `Section purpose`: what the section must accomplish for the reader.
+- `Encouraged expressions`: moves and sentence roles that usually improve paper-facing writing.
+- `Discouraged expressions`: patterns that are sometimes salvageable but should trigger review.
+- `Banned expressions / moves`: patterns that should be removed or rewritten before the round is accepted.
+
+These are paper-facing defaults. They are not project-specific branding rules.
+
+## Abstract
+
+**Section purpose**
+- State the problem, the gap, the proposed approach, the main result, and the main boundary in one compact arc.
+
+**Encouraged expressions**
+- Direct problem statements.
+- Explicit gap language tied to prior work.
+- One-sentence mechanism summaries.
+- Bounded result claims with concrete scope.
+
+**Discouraged expressions**
+- Long setup of benchmark details.
+- Contribution lists that read like the introduction.
+- Excessive future-work framing.
+
+**Banned expressions / moves**
+- Roadmap prose such as "In this paper, we first..., then..., finally...".
+- Reviewer-facing instructions such as "the reader can see" or "as shown clearly below".
+- Unbounded superiority claims such as "universally", "always", or "in every setting".
+
+## Introduction
+
+**Section purpose**
+- Establish the problem, explain why existing work is insufficient, and define the paper's contribution and scope.
+
+**Encouraged expressions**
+- Problem -> gap -> challenge -> contribution progression.
+- Explicit prior-work limitation statements.
+- Clear contribution bullets or equivalent prose.
+- Early explanation of task setting and scope.
+
+**Discouraged expressions**
+- Repeating "important" or "significant" without a concrete consequence.
+- Opening with generic field hype.
+- Listing contributions before the gap is clear.
+
+**Banned expressions / moves**
+- Empty macro-importance claims such as "this problem is increasingly critical" with no concrete consequence.
+- Marketing-style first-claim language such as "revolutionary", "game-changing", or "unprecedented" without evidence.
+- Paragraphs that only praise the paper instead of stating the research gap.
+
+## Related Work
+
+**Section purpose**
+- Position the paper against the most relevant prior work and explain what remains unresolved.
+
+**Encouraged expressions**
+- Topic-grouped comparisons.
+- Closest-prior contrast statements.
+- Short, explicit gap summaries after each cluster.
+
+**Discouraged expressions**
+- Citation dumps with one sentence per paper.
+- Chronological lists without synthesis.
+- Purely positive summaries of prior work.
+
+**Banned expressions / moves**
+- Laundry-list paragraphs that only say "X does..., Y does..., Z does..." with no comparison.
+- Claims that related work is weak or obsolete without specifying the missing capability.
+- Hiding the closest prior work behind broad category language.
+
+## Method
+
+**Section purpose**
+- Explain the mechanism, why each design choice is needed, and what technical advantage it yields.
+
+**Encouraged expressions**
+- Motivation -> design -> technical effect progression.
+- Explicit role statements for modules or steps.
+- Concrete descriptions of information flow and interaction.
+- Local naming bridges when canonical labels appear before their defining section.
+
+**Discouraged expressions**
+- Long implementation detail lists that belong in appendix or setup.
+- Repeating model names without explaining their role.
+- Overusing novelty language instead of mechanism explanation.
+
+**Banned expressions / moves**
+- Marketing-style or self-promotional wording such as "elegant", "powerful", "dramatically stronger", or "significantly outperforms prior methods" when used as prose decoration rather than evidence-backed result reporting.
+- Explaining the method by saying it is "better", "stronger", or "more advanced" without saying how it works.
+- Introducing new narrative aliases for canonical model or ablation labels after they have already been locked.
+
+## Experiments
+
+**Section purpose**
+- State the evaluation protocol, report the result, explain the result, and delimit its meaning.
+
+**Encouraged expressions**
+- Direct statements of protocol, metric definition, and comparison scope.
+- Immediate result reporting with concrete numbers.
+- Short interpretation tied to the table or figure.
+- Explicit limitations or boundary statements after the result.
+
+**Discouraged expressions**
+- Long policy or deployment discussion after every table.
+- Re-explaining the same metric in every paragraph.
+- Paragraphs that only restate the table without synthesis.
+
+**Banned expressions / moves**
+- Meta-reader guidance such as "这样读者可以……", "the reader can first...", or "this table lets the reader...".
+- Self-evaluations such as "结果也很清楚", "the defense results are very clear", or "the table is self-explanatory".
+- Layout-process commentary in scientific prose, such as "由于表列较多，这里采用页宽自适应排版" or "we use page-width adaptive layout here".
+- Claims that a table "proves" something when the evidence only supports a bounded empirical result.
+
+## Conclusion
+
+**Section purpose**
+- Summarize the paper's supported takeaways, restate the boundary, and identify one justified next step.
+
+**Encouraged expressions**
+- Short recap of the paper's supported findings.
+- Boundary or limitation statement.
+- One concrete next step or open question.
+
+**Discouraged expressions**
+- Repeating the full introduction.
+- Adding new benchmark detail or ablation detail.
+- Ending only with broad impact language.
+
+**Banned expressions / moves**
+- Introducing new evidence, new experiments, or new mechanism claims.
+- Expanding the paper's scope beyond what the experiments support.
+- Ending with generic hype such as "this opens a new era" or "this will broadly transform the field".

package/package-assets/shared/skills/lab/stages/write.md

@@ -58,6 +58,7 @@ Run these on every round:
 
 - section flow check -> `skills/lab/references/paper-writing/does-my-writing-flow-source.md`
 - reviewer pass -> `skills/lab/references/paper-writing/paper-review.md`
+- section-specific style policy -> `skills/lab/references/paper-writing/section-style-policies.md` (load the block matching the current section)
 
 ## Small-Step Writing Rules
 
@@ -102,6 +103,16 @@ Run these on every round:
 - If a section must use canonical short names, model labels, or ablation labels before the section that formally introduces them has been drafted, add a local naming bridge in that section that briefly maps the descriptive phrase to the canonical paper-facing labels and then reuse those labels consistently.
 - Keep one canonical natural-language paper-facing name per concept. Do not let one concept drift across paper-facing names, experiment labels, and internal identifiers.
 - Once a paper-facing model or ablation label is chosen, reuse the canonical label in later prose, tables, captions, and ranking summaries instead of replacing it with a narrative alias.
+- Before drafting or polishing, check the current section's block in `section-style-policies.md` and follow its encouraged, discouraged, and banned expression lists.
+- Before any additional tighten, compress, or polish pass on the same section, run a section-level acceptance gate first.
+- The section-level acceptance gate is passed only when canonical naming consistency, adjacent-section consistency, claim, metric, and ranking consistency with the current evidence, local clarity, local concision, and section-style compliance are all explicitly checked and no unresolved blocker remains.
+- If the current section still contains a banned expression or banned rhetorical move from `section-style-policies.md`, the round has not passed the section-level acceptance gate.
+- If the current round changes the paper's canonical experiment or evaluation protocol (for example split ratio, train/test size, seed or split count, benchmark set, or main-table evaluation contract), treat it as a canonical protocol replacement unless the user explicitly scopes it as supplementary or appendix-only.
+- A canonical protocol replacement requires a paper-wide impact audit before more polishing: identify stale sections and assets across Abstract, Introduction, Method, Experiments, Conclusion, tables, figures, analysis assets, and `.lab/writing/plan.md`, then update the plan and highest-impact stale targets first.
+- When a paper-wide impact audit is still open, default the next write action to the highest-impact canonical stale section or asset instead of polishing the same section again.
+- Do not propose or execute translation-layer or workflow-layer synchronization steps unless the user explicitly asked for them or the language-finalization workflow requires them.
+- If any section-level acceptance item is still unresolved, spend the round fixing that blocker instead of doing more prose polish.
+- Do not default the next-step recommendation to another polish pass. Recommend the first unresolved section-level blocker, or stop if the section is already accepted for the round.
 - Use natural-language full names in prose. If an approved short form is needed later, define it once and reuse it consistently.
 - Do not use labels containing `_` or `-` in reader-facing prose.
 - Keep internal identifiers, config keys, and experiment package labels out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose.
@@ -110,6 +121,11 @@ Run these on every round:
 - Short headers remain allowed, but they must be resolved locally through the same table's caption or table note instead of forcing the reader to chase the Method section.
 - If the Method or Experiments prose says the paper reports a metric family, the main table set must either expose those metrics directly or explicitly mark the missing ones as appendix-only and explain why.
 - If a metric is measured but omitted because it is uniformly zero, redundant, or appendix-only, state that disposition explicitly in the caption or table note instead of silently dropping it.
+- Do not treat `\resizebox{\linewidth}{!}{...}` as the default way to fit a main table.
+- Main-table width control should follow this order: shorten headers while preserving local explanations, move secondary metrics to appendix-only, reduce or split columns, adjust `\tabcolsep` conservatively, and only then consider `\resizebox` as a last resort.
+- When `\tabcolsep` is adjusted for a paper-facing main table, keep it in a safe range and avoid shrinking below roughly `3pt`; prefer `4pt` or `5pt` when a small reduction is enough.
+- Do not use `\scriptsize` or `\tiny` as the default main-table fit strategy. If a table only fits after aggressive font shrinking, redesign the table instead of forcing it into the page.
+- If a paper-facing main table uses `\resizebox` or non-default width control, explain the width-control rationale in the same table note.
 - Every main table should have a short table-introduction sentence before it and a short interpretation sentence after it so the reader knows what question the table answers and how to read the result.
 - Build the paper asset plan before prose when the section carries introduction, experimental, method, related-work, or conclusion claims:
   - record the asset coverage targets and gaps for the current paper
@@ -143,6 +159,7 @@ Run these on every round:
   - `<deliverables_root>/paper/analysis/analysis-asset.tex`
 - Table assets must use paper-facing LaTeX structure with `booktabs`, caption, label, and consistent precision.
 - Table assets must also include a local table note that explains row meaning, column meaning, metric definitions, comparison scope, and any important caveat.
+- Table assets must not rely on aggressive width hacks by default; if width control is still needed after table redesign, document it locally and keep it readable.
 - Figure placeholders must explain what the final figure should show and why the reader needs it.
 - Core asset coverage for a paper-facing final draft should include a problem-setting or teaser figure, a method overview figure, a results overview figure, a main-results table, an ablation table, and one additional analysis asset.
 - Keep `.lab/writing/plan.md` synchronized with the current table plan, figure plan, citation plan, and section-to-asset map whenever manuscript assets change.
@@ -156,6 +173,9 @@ Run these on every round:
 - Record what changed and why in a write-iteration artifact.
 - Maintain `.lab/writing/terminology-glossary.md` as the write-stage source for full forms, approved short forms, reader-facing explanations, and aliases whenever terminology changes.
 - When a round introduces or revises key terms, include a compact terminology note in the user-facing round summary and record the terminology-clarity self-check in the write-iteration artifact.
+- Record the section-level acceptance gate in the write-iteration artifact before recommending further tightening on the same section.
+- Record section-style policy compliance, any retained discouraged move, and any banned move found in the write-iteration artifact.
+- Record the protocol/scope impact audit in the write-iteration artifact whenever a round replaces or rewrites a canonical experiment/evaluation protocol.
 - When `workflow_language` and `paper_language` differ, record the final manuscript language choice in the write-iteration artifact with the workflow language, paper language, finalization decision, and why that decision was chosen.
 - When `workflow_language` and `paper_language` differ, also record the persisted workflow-language paper-layer path in the write-iteration artifact.
 - Keep the handoff wording in the write-iteration artifact explicit and stable: say what is completed, what scope is frozen for the next round, what the next owner is allowed to do, what they must read first, and what counts as accept, revise, or reject.
@@ -202,4 +222,6 @@ Run these on every round:
 - If a missing assumption would change the section structure or claim strength, ask one clarifying question at a time.
 - If there are multiple defensible narrative structures for the current section, present 2-3 approaches with trade-offs and recommend one before drafting.
 - Keep an approval gate when the chosen narrative structure would materially affect downstream sections or paper-level framing.
+- If the user asks to continue tightening the same section, default to a section-level acceptance review first instead of another immediate prose-polish pass.
+- Only recommend another tighten/compress/polish pass after the current section has passed the section-level acceptance gate.
 - If the round introduces or revises key terms, abbreviations, metrics, or mechanism names, include a short terminology note in the final user-facing response that says the full form, approved short form if any, what each term is, and why it matters here, and point to `.lab/writing/terminology-glossary.md` plus the write iteration artifact for the full terminology audit.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlab",
-  "version": "0.1.55",
+  "version": "0.1.57",
   "description": "Strict /lab research workflow installer for Codex and Claude",
   "keywords": [
     "codex",